{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T03:27:53Z","timestamp":1785900473893,"version":"3.56.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000943","name":"Commonwealth Scientific and Industrial Research Organisation","doi-asserted-by":"publisher","award":["50092128"],"award-info":[{"award-number":["50092128"]}],"id":[{"id":"10.13039\/501100000943","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARC-Discovery","award":["DP220100800"],"award-info":[{"award-number":["DP220100800"]}]},{"name":"ARC-DECRA","award":["DE230100477"],"award-info":[{"award-number":["DE230100477"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3405622","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T17:31:02Z","timestamp":1717003862000},"page":"10015-10028","source":"Crossref","is-referenced-by-count":31,"title":["BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3159-0034","authenticated-orcid":false,"given":"Chen","family":"Liu","sequence":"first","affiliation":[{"name":"University of Queensland, St. Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peike","family":"Li","sequence":"additional","affiliation":[{"name":"MatrixVerse AI, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9892-9515","authenticated-orcid":false,"given":"Hu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Queensland, St. Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6047-0472","authenticated-orcid":false,"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-4949","authenticated-orcid":false,"given":"Zi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Queensland, St. Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0409-2259","authenticated-orcid":false,"given":"Dadong","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO, Data61, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-5649","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Queensland, St. Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/a0023175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2011.00212"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886263"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2871418"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2238522"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2228476"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2937185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3407692"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20073"},{"key":"ref15","article-title":"A closer look at weakly-supervised audio-visual source localization","author":"Mo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00517"},{"key":"ref17","first-page":"386","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref21","article-title":"Improving audio-visual video parsing with pseudo visual labels","author":"Zhou","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref23","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Oya","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00222"},{"key":"ref26","first-page":"3222","article-title":"Self-supervised predictive learning: A negative-free method for sound source localization in visual scenes","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Song","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747867"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref30","first-page":"10317","article-title":"Consistent structural relation learning for zero-shot segmentation","volume":"33","author":"Li","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413944"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"ref38","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref39","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","author":"Bao"},{"key":"ref40","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref41","first-page":"1532","article-title":"Glove: Global vectors for word representation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Pennington","year":"2014"},{"key":"ref42","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10541892.pdf?arnumber=10541892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:36:20Z","timestamp":1729226180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10541892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3405622","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}